© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8790
    Prev
    Next
    INDEX
    Explanations

    technical data related to studies, machine specifications, or protocol versions

    oai_token-act-pair · gemini-2.0-flash

    say "data"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Data
    -3.13
    Data
    -2.92
     data
    -2.89
     DATA
    -2.80
    data
    -2.72
    DATA
    -2.64
     Daten
    -2.34
    データ
    -2.22
    数据
    -2.19
    的数据
    -2.17
    POSITIVE LOGITS
    :+:
    0.52
    findpost
    0.51
    peutic
    0.50
    kloped
    0.49
     minOccurs
    0.49
     vectorielles
    0.48
    expandindo
    0.48
     épais
    0.47
     remercier
    0.47
    CloseOperation
    0.46
    Activations Density 3.721%

    No Known Activations